Scribd
Upload
27 views

Exer Design Based Estimation2

This document describes probability-proportional to size (PPS) sampling with replacement to estimate the mean and total income from a population of households across 10 barangays. A sample of 4 barangays was selected with PPS, and the mean income was estimated as PHP 128,009.62 with a standard error of PHP 21,335.07. The total income across all barangays was estimated as PHP 12,800,962.18 with a standard error of PHP 2,133,507.07. Formulas for PPS estimators and their variances are provided.

Uploaded by

Jhoanne Ynion
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
27 views

Exer Design Based Estimation2

This document describes probability-proportional to size (PPS) sampling with replacement to estimate the mean and total income from a population of households across 10 barangays. A sample of 4 barangays was selected with PPS, and the mean income was estimated as PHP 128,009.62 with a standard error of PHP 21,335.07. The total income across all barangays was estimated as PHP 12,800,962.18 with a standard error of PHP 2,133,507.07. Formulas for PPS estimators and their variances are provided.

Uploaded by

Jhoanne Ynion
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

STAT 166: STATISTICS FOR SOCIAL SCIENCES

Exercise: Design-Based Estimation

Probability-Proportional to Size with replacement


Let Yi = the value for the ith unit in the population
Xi = the auxiliary variable
Pi = the probability of selecting the ith unit in the population
where i = 1,2,N, Hence,
N

P
i =1

= 1; Pi = Xi

x
i =1

Estimator

Yi

Mean

ypps=z= zi n;zi =
i=1

Variance

2
z

s = zi z
i=1

NPi

; i = 1, 2, ..., N

n 1

Variance of
2
V
y
=V
z
=s
n
pps
z
the mean

( ) ()

Total
Variance of
the total

T Y =Nz;zi = Yi Pi ; i = 1, 2, ..., N

()

V Nz =N2s2z n

( )

STAT166 1ST SEM 2012-2013 JCYnion

STAT 166: STATISTICS FOR SOCIAL SCIENCES


Exercise: Design-Based Estimation

EXAMPLE:
A municipality has ten barangays with 150, 50, 80, 100, 200, 160,
40, 220, 60, and 140 households, respectively. It is desired to
select a sample of 4 barangays with replacement and with
probabilities proportional to the number of households in the
barangay. Suppose the barangay selected are 6th, 6th, 8th and 4th.
a. Estimate the mean gross income they had in the previous year
and its measure of precision.
Bgy

No. of
Household
(Xi)

Income
(Yi)

160

150,000

160

150,000

220

350,000

100

80,000

Pi = x i
160
1200
160
P2 =
1200
220
P3 =
1200
100
P4 =
1200

P1 =

x
i =1

zi =

Yi
NPi

150,000
10 * 0.1333
150,000
= 0.1333 z 2 =
10 * 0.1333
350,000
= 0.1833 z 3 =
10 * 0.1833
80,000
= 0.0833 z 4 =
10 * 0.0833

= 0.1333 z1 =

1 n
512038.4874
= z = zi =
= 128,009.6218
n i =1
4

y pps

s = zi z
2
z

i =1

n 1 = 1,820,740,962

1,820,740,962

Var y pps =
= 455,185,240.5
4

se y pps = 455,185,240.5 = 21,335.07067

STAT166 1ST SEM 2012-2013 JCYnion

STAT 166: STATISTICS FOR SOCIAL SCIENCES


Exercise: Design-Based Estimation

b. Estimate the total gross income they had in the previous year
and its measure of precision.
No. of
Household
(Xi)

Income
(Yi)

160

150,000

160

150,000

220

350,000

100

80,000

Bgy

Pi = x i
160
1200
160
P2 =
1200
220
P3 =
1200
100
P4 =
1200

P1 =

x
i =1

z i = Y i Pi

150,000
0.1333
150,000
= 0.1333 z 2 =
0.1333
350,000
= 0.1833 z 3 =
0.1833
80,000
= 0.0833 z 4 =
0.0833

= 0.1333 z1 =

T Y = Nz = 10 *1,280,096.218 = 12,800,962.18

( )

s =
2
z

(z
i =1

= 182,074,096,200

n 1
102 *182,074,096,200
Var T =
= 4,551,852,405,000
4

( )

se T = 4,551,852, 405,000 = 2,133,507.067

( )

STAT166 1ST SEM 2012-2013 JCYnion

You might also like